Microsoft Phi-4 Reasoning, Microsoft Phi-4 Reasoning Plus and Microsoft Phi-4 Mini Reasoning SLMs Launched Today, All Achieve Higher Performance on Complex Tasks
Microsoft Phi-4 Reasoning, Microsoft Phi-4 Reasoning Plus, and Microsoft Phi-4 Mini Reasoning SLMs are launched today. All the new small-language models achieve higher performance on complex tasks.
Microsoft Phi-4 Reasoning, Microsoft Phi-4 Reasoning Plus and Microsoft Phi-4 Mini Reasoning models launched today in the Phi-4 AI model family. The new reasoning SLM models achieve higher performance on complex reasoning tasks. The tech giant said that the Microsoft Phi-4 reasoning models were trained to leverage the time-scaling to perform complex tasks that require multi-step "decomposition and internal reflection." Phi-4 reasoning is a 14B (14 billion) parameter open-weight reasoning model, an SLM that is capable of rivalling LLMs. ‘Goodbye GPT-4’: OpenAI CEO Sam Altman Bids Farewell to AI Model That Started Revolution in 2023 by Offering Significant Improvement Over GPT-3 Model.
Phi-4 Reasoning Models Launched by Microsoft
We’ve been cooking... a new open weights 14B Phi-4 reasoning model, SFT’d on ~1.4M carefully curated reasoning demonstrations from o3-mini and RL’d for a tiny bit. This model is a little beast. pic.twitter.com/4xJuvYpZBH
— Dimitris Papailiopoulos (@DimitrisPapail) May 1, 2025
(The above story first appeared on LatestLY on May 01, 2025 02:07 PM IST. For more news and updates on politics, world, sports, entertainment and lifestyle, log on to our website latestly.com).
